SpikeYOLO-Boost: a spiking neural network for remote sensing object detection based on an attention mechanism

Traditional convolutional neural networks suffer from excessive energy consumption, which restricts their edge deployment for object detection in remote sensing images. Brain-inspired spiking neural networks (SNNs) offer biological plausibility and low-power advantages. At present, the performance of SNNs on object detection tasks still trails behind mainstream models, particularly in complex remote sensing scenes characterized by large-scale variations, cluttered backgrounds, and dense small objects. In this paper, we aim to improve the performance of SNNs for object detection in remote sensing images. We propose the SpikeYOLO-Boost framework. First, we design the SpikeBoT3 spiking hybrid backbone module, which establishes a dual-path global modeling mechanism in the spike domain. Then, we design the SpikeSEAttention spiking channel attention mechanism, which leverages temporal average pooling to achieve channel-wise enhancement in the spike domain, thereby improving feature fusion and robustness.

1. Wang Z., Fang Q., Han D. Research progress of on-orbit intelligent processing technology for imaging satellites. Journal of Astronautics, 2022, vol. 43, no. 3, pp. 259–270 (in Chinese). https://doi.org/10.3873/j.issn.1000-1328.2022.03.001

2. Cheng L., Liu X., Li L., Jiao L., Tang X. Deep adaptive proposal network for object detection in optical remote sensing images. arXiv, 2018. https://doi.org/10.48550/arXiv.1807.07327

3. Li Y., Wang M., Hwang K., Li Z., Ji T. LEO satellite constellation for global-scale remote sensing with on-orbit cloud AI computing. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2023, vol. 16, pp. 9369– 9381. https://doi.org/10.1109/JSTARS.2023.3316298

4. Cai C., Zhu Y., Sheng M., Li J., Shi Y., Zhou D., Xie Z., Zhang C. 3C resources joint allocation for time-deterministic remote sensing image backhaul in the space-ground integrated network. arXiv, 2025. https://doi.org/10.48550/arXiv.2510.09409

5. Luo X., Yao M., Chou Y., Xu B., Li G. Integer-valued training and spike-driven inference spiking neural network for high-performance and energy-efficient object detection. arXiv, 2025. https://doi.org/10.48550/arXiv.2407.20708

6. Xiao Y., Yuan Q., Jiang K., Huang W., Zhang Q., Zheng T., Lin C.-W., Zhang L. Spiking meets attention: Efficient remote sensing image super-resolution with attention spiking neural networks. arXiv, 2025. https://doi.org/10.48550/arXiv.2503.04223

7. Vaswani A., Shazeer N., Parmar N., Uszkoreit J., Jones L., Gomez A. N., Kaiser Ł., Polosukhin I. Attention is all you need. arXiv, 2023. https://doi.org/10.48550/arXiv.1706.03762

8. Srinivas A., Lin T.-Y., Parmar N., Shlens J., Abbeel P., Vaswani A. Bottleneck transformers for visual recognition. arXiv, 2021. https://doi.org/10.48550/arXiv.2101.11605

9. Hu J., Shen L., Albanie S., Sun G., Wu E. Squeeze-and-Excitation networks. arXiv, 2019. https://doi.org/10.48550/arXiv.1709.01507

10. Long Y., Gong Y., Xiao Z., Liu Q. Accurate object localization in remote sensing images based on convolutional neural networks. IEEE Transactions on Geoscience and Remote Sensing, 2017, vol. 55, no. 5, pp. 2486–2498. https://doi.org/10.1109/TGRS.2016.2645610

11. Xiao Z., Liu Q., Tang G., Zhai X. Elliptic Fourier transformation-based histograms of oriented gradients for rota­ tionally invariant object detection in remote-sensing images. International Journal of Remote Sensing, 2015, vol. 36, no. 2, pp. 618–644. https://doi.org/10.1080/01431161.2014.999881

12. Panda P., Aketi S. A., Roy K. Toward scalable, efficient, and accurate deep spiking neural networks with backward residual connections, stochastic softmax, and hybridization. Frontiers in Neuroscience, 2020, vol. 14, art. 653. https://doi.org/10.3389/fnins.2020.00653

13. Horowitz M. 1.1 computing’s energy problem (and what we can do about it). IEEE International Solid-State Circuits Conference Digest of Technical Papers (ISSCC), San Francisco, 2014, pp. 10–14. https://doi.org/10.1109/isscc.2014.6757323